JP2022093261A - Database generator, state determination device, database generation method, and state determination method - Google Patents

Abstract

To provide a database generator capable of easily collecting data as a reference for determining the state of a fluid pressure driving valve.SOLUTION: A database generator 6 includes: a storage unit 60 which stores a database 2 in which determination reference data as a reference of an operation state when opening and closing operation is performed at a fluid pressure driving valve 1 can be registered; a virtual load unit 61 which is capable of virtually reproducing a load state when a main valve 3 is driven under use environment 10 for a combination of the use environment 10 and the main valve 3; a test data acquisition unit 62 which acquires determination reference data when the opening and closing operation is performed at a virtual fluid pressure driving valve 1a composed of the virtual load unit 61, in which a load state for reproducing the use environment 10 and the main valve 3 to be tested is set, and a driving device 4 and an electromagnetic valve 5 to be tested; and a database registration unit 63 which registers, in the database 2, the combination of targets to be tested in association with the determination reference data acquired at the virtual fluid pressure driving valve 1a.SELECTED DRAWING: Figure 5

Description

The present invention relates to a database generation device, a state determination device, a database generation method, and a state determination method.

Conventionally, a fluid pressure drive valve that controls a drive fluid by a solenoid valve and opens and closes a main valve via a valve shaft driven by a drive device is known. For example, Patent Document 1 describes, as a fluid pressure drive valve used for piping of plant equipment, a ball valve (a ball valve via a drive device) in which the drive fluid is controlled by a solenoid valve in an emergency such as when an abnormality occurs in the equipment. An emergency isolation valve device that shuts off the fluid flowing through the pipe by closing the main valve) is disclosed.

Japanese Unexamined Patent Publication No. 2009-97539

In a fluid pressure driven valve such as an emergency isolation valve used in plant equipment as disclosed in Patent Document 1, in order to improve the operating rate and reliability of the entire plant equipment, the state of the fluid pressure driven valve should be grasped. It is desirable to do. At that time, if there is data (determination reference data) as a reference for determining the state of the fluid pressure drive valve, it is possible to accurately grasp the state of the fluid pressure drive valve.

However, the fluid pressure drive valve is provided with a main valve, a drive device, and a solenoid valve as its configuration, and there are a plurality of types based on the usage environment in which the main valve is used, the specifications required for the fluid pressure drive valve, and the like. A specific combination is selected and manufactured from a main valve, a plurality of types of drive devices, and a plurality of types of solenoid valves. Therefore, it has been a lot of time and effort to prepare the judgment standard data in advance for each combination of the four elements of the usage environment, the main valve, the drive device, and the solenoid valve.

The present invention has been made in view of the above problems, and is a database generation device, a state determination device, and a database that enable easy collection of reference data for determining the state of a fluid pressure drive valve. It is an object of the present invention to provide a generation method and a state determination method.

In order to achieve the above object, the database generator according to one aspect of the present invention is
It is composed of a main valve used in a predetermined usage environment, a drive device for driving a valve shaft connected to the main valve, and a solenoid valve for controlling supply and discharge of a drive fluid to the drive device. A database generator that generates a database used to determine the state of a fluid pressure driven valve.
A predetermined opening / closing operation can be performed by the fluid pressure drive valve for each combination of the plurality of types of usage environments, the plurality of types of the main valve, the plurality of types of drive devices, and one or more types of the solenoid valves. A storage unit that stores the database that can be registered in association with each other as a criterion data that serves as a reference for the operating state when the operation is performed.
A virtual load unit that can virtually reproduce the load state when the main valve is driven in the usage environment for each combination of the plurality of types of the usage environment and the plurality of types of the main valve.
The virtual fluid pressure composed of the virtual load unit in which the usage environment to be tested and the load state that reproduces the main valve are set, the drive device to be tested, and the solenoid valve. A test data acquisition unit that acquires the judgment reference data when the opening / closing operation is performed by the drive valve, and a test data acquisition unit.
The determination reference data acquired by the virtual fluid pressure drive valve is associated with the combination of the usage environment, the main valve, the drive device, and the solenoid valve to be tested. It has a database registration unit for registering in the database.

According to the database generation device according to one aspect of the present invention, the test data acquisition unit includes a virtual load unit in which the usage environment to be tested and a load state for reproducing the main valve are set, a drive device to be tested, and a drive device to be tested. Judgment standard data when opening / closing operation is performed by a virtual fluid pressure drive valve composed of an electromagnetic valve is acquired, and the database registration unit determines the usage environment to be tested, the main valve, the drive device, and the electromagnetic wave. The judgment standard data acquired by the virtual fluid pressure drive valve is associated with the combination with the valve and registered in the database.

Therefore, a virtual fluid pressure drive valve is configured by reproducing the load state according to the combination of the usage environment and the main valve to be tested by the virtual load unit. It is not necessary to prepare the actual equipment accordingly, and the judgment standard data when the opening / closing operation is performed by the virtual fluid pressure drive valve is acquired. Therefore, the determination reference data can be easily collected for each combination of the four elements of the usage environment, the main valve, the drive device, and the solenoid valve.

Issues, configurations and effects other than the above will be clarified in the form for carrying out the invention described later.

It is an overall block diagram which shows an example of the operation support system 100 of the fluid pressure drive valve 1 which concerns on embodiment of this invention. It is a schematic block diagram which shows an example of the fluid pressure drive valve 1 which concerns on embodiment of this invention. It is a schematic block diagram which shows an example of the fluid pressure drive valve 1 which concerns on embodiment of this invention. It is a hardware block diagram which shows an example of the computer 200 which constitutes the database generation apparatus 6 and the state determination apparatus 7 which concerns on embodiment of this invention. It is a schematic block diagram which shows an example of the database generation apparatus 6 which concerns on embodiment of this invention. It is a data structure diagram which shows an example of the database 2 which concerns on embodiment of this invention. It is a flowchart which shows an example of the database generation method by the database generation apparatus 6 which concerns on embodiment of this invention. It is a schematic block diagram which shows an example of the state determination apparatus 7 which concerns on embodiment of this invention. It is a flowchart which shows an example of the state determination method by the state determination apparatus 7 which concerns on embodiment of this invention. It is a data structure diagram which shows the modification of the database 2 which concerns on embodiment of this invention. It is a figure explaining the learning phase of machine learning in the modification of the learning model which concerns on embodiment of this invention. It is a figure explaining the inference phase of machine learning in the modification of the learning model which concerns on embodiment of this invention.

Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. In the following, the scope necessary for the explanation for achieving the object of the present invention will be schematically shown, and the scope necessary for the explanation of the relevant part of the present invention will be mainly described. It shall be based on technology.

FIG. 1 is an overall configuration diagram showing an example of an operation support system 100 for a fluid pressure drive valve 1 according to an embodiment of the present invention.

The fluid pressure drive valve 1, which is the target of operation support in the operation support system 100, is installed in a pipe 11 through which control fluids such as various gases and petroleum flow, for example, in plant equipment, infrastructure equipment, and the like. The fluid pressure drive valve 1 is used as an emergency shutoff valve for shutting off the flow of the pipe 11 at the time of an emergency stop such as when some abnormality occurs in the equipment. The equipment and applications in which the fluid pressure drive valve 1 is installed are not limited to the above examples.

The fluid pressure drive valve 1 has, as its main configuration, a main valve 3 arranged in the middle of a pipe 11, a drive device 4 for driving a valve shaft 12 connected to the main valve 3, and a drive device 4. It is composed of a solenoid valve 5 that controls the supply and discharge of a driving fluid. Further, if an abnormality occurs in the fluid pressure drive valve 1 itself, the function as an emergency isolation valve as described above is impaired. Therefore, the fluid pressure drive valve 1 is in a state of the fluid pressure drive valve 1 according to a predetermined state determination condition. It is equipped with a status determination function for monitoring (for example, presence / absence of abnormality, determination of remaining life, etc.).

The main valve 3, the drive device 4, and the solenoid valve 5 as components constituting the fluid pressure drive valve 1 have a plurality of types of main valves according to various specifications (structure, size, material, performance, etc.). 3 (3 ₁ , 32, ..., _{3 q} ), multiple types of drive devices 4 (4 ₁ , 4 ₂ , ..., 4 _r ), and multiple types of solenoid valves 5 (5 ₁ , ₅₂ , ..., 5 _s ) and each exist. Further, the usage environment 10 in which the fluid pressure drive valve 1 is used differs in various conditions such as the type and pressure of the control fluid flowing through the pipe 11 and the condition of the place of use (outdoor or indoor, outside air temperature, humidity, etc.). Therefore, a plurality of types of usage environments 10 (10 ₁ , 10 ₂ , ..., 10 _p ) are assumed. The subscripts p, q, r, and s are arbitrary integers and indicate the number of types of the usage environment 10, the main valve 3, the drive device 4, and the solenoid valve 5, respectively.

Therefore, in the fluid pressure drive valve 1, the specifications of the fluid pressure drive valve 1 are determined according to the usage environment 10, and the type of the main valve 3 and the drive of the fluid pressure drive valve 1 are as components that satisfy the specifications of the fluid pressure drive valve 1. The type of the device 4 and the type of the solenoid valve 5 are selected. The fluid pressure drive valve 1 is manufactured by assembling the main valve 3, the drive device 4, and the solenoid valve 5 according to the combination in which each type is selected. The type is specified by, for example, a model name, a model name, a model number, and the like.

In the fluid pressure drive valve 1 manufactured as described above, it is difficult to uniformly set the state determination conditions, and the state determination is made according to the combination of the usage environment 10, the main valve 3, the drive device 4, and the solenoid valve 5. It is necessary to operate with the conditions set appropriately. The operation support system 100 of the fluid pressure drive valve 1 generates a database 2 for setting a state determination condition for such a fluid pressure drive valve 1, and operates the fluid pressure drive valve 1 using the database 2. Functions as a system to support.

The operation support system 100 for the fluid pressure drive valve 1 has, as its main configuration, a database generation device 6 for generating a database 2 used for determining the state of the fluid pressure drive valve 1 and a fluid pressure using the database 2. A state determination device 7 for determining the state of the drive valve 1 is provided.

The database generation device 6 includes a database 2 capable of registering judgment reference data as a state judgment condition for each combination of the usage environment 10, the main valve 3, the drive device 4, and the solenoid valve 5, and the judgment registered in the database 2 is provided. The reference data is provided to the state determination device 7.

The state determination device 7 refers to the database 2 and determines the state of the fluid pressure drive valve 1 based on the determination reference data registered in the database 2 and the determination target data measured by the fluid pressure drive valve 1. ..

In the following, first, the details of the fluid pressure drive valve 1 which is the target of the operation support by the operation support system 100 will be described, and then the details of the database generation device 6 and the state determination device 7 will be described.

(Fluid pressure drive valve 1)
FIG. 2 is a schematic configuration diagram showing an example of the fluid pressure drive valve 1 according to the embodiment of the present invention. The fluid pressure drive valve 1 includes a main valve 3, a drive device 4, and a solenoid valve 5.

The fluid pressure drive valve 1 shown in FIG. 2 employs an airless closing method. During steady operation, the main valve 3 is opened by supplying air A (supply air) from the air supply source 13 to the drive device 4 via the solenoid valve 5, and is driven during an emergency stop or test operation. The main valve 3 is closed by discharging air A (exhaust) from the device 4 via the solenoid valve 5. The fluid pressure drive valve 1 may adopt an airless open system. In that case, the fluid pressure drive valve 1 is closed by supplying air A to the drive device 4, and the air A is discharged from the drive device 4. The main valve 3 is opened at.

In the fluid pressure drive valve 1, as a flow path of air A, a first air pipe 130 connecting between the air supply source 13 and the solenoid valve 5 and a second air pipe 130 connecting between the solenoid valve 5 and the drive device 4 are connected. The air pipe 131 is provided. The driving fluid is not limited to the above-mentioned air A, and may be another gas or a liquid (for example, oil).

A communication cable 140 for transmitting and receiving various data between the external device 14 and the solenoid valve 5 and a power cable 150 for supplying electric power from the external power supply 15 to the solenoid valve 5 are connected to the fluid pressure drive valve 1.

The external device 14 is a device that transmits and receives various information to and from the fluid pressure drive valve 1. The external device 14 is composed of, for example, a computer for equipment management (including a local server and a cloud server), a computer for workers, a storage device for data storage, a storage medium, and the like. As for the communication between the external device 14 and the solenoid valve 5, any communication standard is adopted, and wireless communication may be used.

A ball valve is adopted as the main valve 3 shown in FIG. As a specific configuration thereof, the main valve 3 includes a valve box 30 arranged in the middle of the pipe 11 and a ball-shaped valve body 31 rotatably provided in the valve box 30, and the valve body 31 is provided. A valve shaft 12 is connected to the upper part of the valve shaft 12. The valve body 31 rotates in the valve box 30 in response to the valve shaft 12 being rotated from 0 to 90 degrees, and the main valve 3 is switched between the fully open state (the state shown in FIG. 2) and the fully closed state. Be done. The valve used as the main valve 3 is not limited to the ball valve, and may be, for example, a butterfly valve or another on / off valve.

The drive device 4 shown in FIG. 2 employs a single-actuated air cylinder mechanism. As a specific configuration thereof, the drive device 4 includes a cylinder 40 having a spring chamber 47 and a cylinder chamber 48, and a pair of pistons 42A provided in the cylinder 40 so as to be reciprocally linearly movable and connected via a piston rod 41. 42B, a coil spring 43 provided in the spring chamber 47 on the first piston 42A side, an air supply / discharge port 44 connected to the cylinder chamber 48 on the second piston 42B side, and a cylinder 40 along the radial direction. It is provided with a transmission mechanism 45 provided at a portion where the valve shaft 12 arranged so as to penetrate the piston rod 41 and the piston rod 41 are orthogonal to each other. The drive device 4 is not limited to the single operation type, and may be configured in another form such as, for example, a double operation type.

The first piston 42A is urged by the coil spring 43 in the direction of closing the main valve 3. The second piston 42B is pressed in the direction of opening the main valve 3 against the urging force of the coil spring 43 by the air A (air supply) supplied from the air supply / discharge port 44. The transmission mechanism 45 is composed of a rack and pinion mechanism, a scotch yoke mechanism, a link mechanism, a cam mechanism, etc., and converts the reciprocating linear motion of the piston rod 41 into a rotary motion and transmits it to the valve shaft 12. ..

The solenoid valve 5 shown in FIG. 2 employs a two-position, normally closed type (“open” when energized, “closed” when not energized) three-way solenoid valve. As a specific configuration of the solenoid valve 5, the spool portion 51 that switches the flow path through which the air A flows is displaced inside the accommodating portion 50, and the spool portion 51 is displaced according to the energized state (when energized or not energized). It is provided with a solenoid unit 52 for causing the solenoid valve 5, and a sensor group 53 for measuring physical quantities and state quantities of each portion of the solenoid valve 5. The solenoid valve 5 is not limited to a two-position, normally closed type three-way solenoid valve, but may be a three-position solenoid valve, a normally open type, a four-way solenoid valve, or the like, and is composed of various formations based on any combination. May be.

The accommodating portion 50 functions as a housing for an indoor type or explosion-proof solenoid valve 5. The accommodating portion 50 includes a shaft insertion port 500 into which the valve shaft 12 (third shaft 12c) is inserted, and a cable insertion port 501 into which the communication cable 140 and the power cable 150 are inserted.

The spool portion 51 has an input port 510 connected to the air supply source 13 via the first air pipe 130, an output port 511 connected to the drive device 4 via the second air pipe 131, and a drive device. It is provided with an exhaust port 512 for discharging the exhaust from 4.

The solenoid unit 52 displaces the spool unit 51 so as to communicate between the input port 510 and the output port 511 when energized, and communicates between the output port 511 and the exhaust port 512 when the power is off. , The spool portion 51 is displaced.

The sensor group 53 is arranged in various places inside the accommodating portion 50. The sensor group 53 includes, for example, a first pressure sensor 530 that measures the fluid pressure of air A flowing through the first flow path 502 communicating with the input port 510, and a second flow path 503 communicating with the output port 511. The second pressure sensor 531 that measures the fluid pressure of the flowing air A and the rotation angle when the valve shaft 12 (third shaft 12c) rotates are measured, and the main valve 3 is measured according to the rotation angle. It is provided with a main valve opening sensor 532 for acquiring valve opening information.

The main valve opening sensor 532 is composed of, for example, a magnetic sensor, measures the magnetic strength generated by the permanent magnet 120 attached to the valve shaft 12 (third shaft 12c), and measures the magnetic strength. Correspondingly, the valve opening information of the main valve 3 is acquired.

The valve shaft 12 is formed in the shape of a rotatable shaft, and is composed of a first shaft 12a, a second shaft 12b, and a third shaft 12c. Both ends of the first shaft 12a are connected to the second shaft 12b and the third shaft 12c, respectively, via a coupling, a connector, or the like, and the first shaft 12a, the second shaft 12b, and the third shaft 12a are connected to each other. The shaft 12c is arranged coaxially. The first shaft 12a is arranged so as to penetrate the drive device 4 and is driven by the drive device 4. The second shaft 12b is connected to the first shaft 12a and is connected to the main valve 3. The third shaft 12c is connected to the first shaft 12a and is inserted into the accommodating portion 50 of the solenoid valve 5 to be pivotally supported. The valve shaft 12 rotates as a whole in synchronization with the driving of the first shaft 12a by the drive device 4.

In the fluid pressure drive valve 1 having the above configuration, when the solenoid valve 5 is energized, the air A (supply air) from the air supply source 13 is the first air pipe 130, the input port 510, and the output. The second piston 42B is pressed and the coil spring 43 is compressed by flowing in the order of the port 511 and the second air pipe 131 and being supplied to the air supply / discharge port 44. Then, when the first shaft 12a (valve shaft 12) is rotated via the piston rod 41 and the transmission mechanism 45 by the amount that the piston rod 41 moves in response to the compression of the coil spring 43, the inside of the valve box 30 The valve body 31 rotates, and the main valve 3 is operated to the fully open state.

On the other hand, when the solenoid valve 5 is in the non-energized state, the air A (exhaust) in the cylinder 40 flows from the air supply / exhaust port 44 to the second air pipe 131, the output port 511, and the exhaust port 512 in this order. By being discharged to the outside air, the pressing force of the second piston 42B is reduced, and the coil spring 43 is restored from the compressed state. Then, when the first shaft 12a (valve shaft 12) is rotated via the transmission mechanism 45 by the amount that the piston rod 41 moves in response to the restoration of the coil spring 43, the valve body 31 is moved in the valve box 30. It rotates and the main valve 3 is operated in a fully closed state.

FIG. 3 is a schematic block diagram showing an example of the fluid pressure drive valve 1 according to the embodiment of the present invention. As shown in FIG. 3, the solenoid valve 5 communicates with the control unit 54 that controls the solenoid valve 5 and the external device 14 in addition to the solenoid unit 52 and the sensor group 53 as an example of the electrical configuration. The communication unit 55 and the power supply circuit unit 56 connected to the external power supply 15 are provided.

In addition to the first pressure sensor 530, the second pressure sensor 531 and the main valve opening sensor 532, the sensor group 53 includes a voltage sensor 533 that measures the supply voltage to the solenoid unit 52, and energization in the solenoid unit 52. A current / resistance sensor 534 that measures the current value at the time and a resistance value when the power is off, a temperature sensor 535 that measures the internal temperature of the housing unit 50, and a magnetic sensor that measures the magnetic strength generated by the solenoid unit 52. It is equipped with 536.

Further, the sensor group 53 measures at least one of the total energization time for the solenoid unit 52 and the current energization continuous time as the operating time of the fluid pressure drive valve 1 as a sensor group for acquiring information on the operation history of each unit. It includes an operation time meter (timer) 537 and an operation counter (counter) 538 that counts the number of operations of each of the solenoid valve 5, the drive device 4, and the main valve 3.

The sensor group 53 is not limited to the one in which the sensors are individually provided as described above, and the specific sensor also has the function of the other sensor, so that the other sensors may not be individually provided. .. For example, the magnetic sensor 536 measures the magnetic strength generated by the solenoid unit 52, and the current / resistance sensor 534 obtains the current value when the solenoid unit 52 is energized based on the magnetic strength. It does not have to be provided individually. Further, the controller 540 may have a built-in sensor function or realize a part of the sensor function. For example, the controller 540 operates by incorporating an operating time meter 537 and an operation counter 538. The time meter 537 and the operation counter 538 may not be provided separately.

The control unit 54, the communication unit 55, and the power supply circuit unit 56 are composed of, for example, a general-purpose or dedicated computer (see FIG. 4 described later).

The control unit 54 processes information indicating the physical quantity and state quantity of each part of the fluid pressure drive valve 1 measured by the sensor group 53, and also controls the controller 540 and the solenoid unit 52 that control each part of the fluid pressure drive valve 1. It is provided with a valve test switch 541 that controls the energized state and opens and closes the main valve 3 during a test operation.

For example, the state determination device 7 is incorporated in the controller 540, and the controller 540 includes a function for realizing the state determination device 7. The configuration of all or part of the state determination device 7 may be realized by another device, for example, another device connected to the external device 14 or the fluid pressure drive valve 1.

The valve test switch 541 receives a command from the controller 540 when a predetermined test operation condition is satisfied, and executes a stroke test of the fluid pressure drive valve 1 as a test operation for performing a predetermined opening / closing operation.

The stroke test is performed, for example, by either a full stroke test or a partial stroke test. The full stroke test is executed by operating the main valve 3 in the fully closed state by switching from the energized state to the non-energized state in the fully open state, and returning it to the fully open state by switching from the non-energized state to the energized state in the fully closed state. Will be done. In the partial stroke test, the main valve 3 is switched from the energized state to the non-energized state in the fully open state without operating the main valve 3 in the fully closed state (that is, without stopping the equipment) to reach a predetermined opening. It is executed by partially closing and returning to the fully open state by switching from the non-energized state to the energized state in the partially closed state.

As the test operation conditions, for example, the execution time or a specific designated date and time according to the execution frequency (for example, once a year) specified as the set value by the administrator has arrived, or the execution command from the external device 14 has arrived. Is accepted, or when the test execution button (not shown) provided on the solenoid valve 5 is operated by the administrator, the test operation (stroke test) is executed so that the test operation condition is satisfied. Just do it.

FIG. 4 is a hardware configuration diagram showing an example of a computer 200 constituting the database generation device 6 and the state determination device 7 according to the embodiment of the present invention.

Each of the database generation device 6 and the state determination device 7 is composed of a general-purpose or dedicated computer 200. As shown in FIG. 4, the computer 200 has, as its main components, a bus 210, a processor 212, a memory 214, an input device 216, a display device 218, a storage device 220, a communication I / F (interface) unit 222, and an external device. It includes a device I / F unit 224, an I / O (input / output) device I / F unit 226, and a media input / output unit 228. The above components may be omitted as appropriate depending on the intended use of the computer 200.

The processor 212 is composed of one or a plurality of arithmetic processing units (CPU, MPU, GPU, DSP, etc.) and operates as a control unit that controls the entire computer 200. The memory 214 stores various data and the program 230, and is composed of, for example, a volatile memory (DRAM, SRAM, etc.) that functions as a main memory, and a non-volatile memory (ROM, flash memory, etc.).

The input device 216 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, and the like. The display device 218 is composed of, for example, a liquid crystal display, an organic EL display, electronic paper, a projector, or the like. The input device 216 and the display device 218 may be integrally configured as in the touch panel display. The storage device 220 is composed of, for example, an HDD, an SSD, or the like, and stores various data necessary for executing the operating system and the program 230.

The communication I / F unit 222 is connected to a network 240 such as the Internet or an intranet by wire or wirelessly, and transmits / receives data to / from another computer according to a predetermined communication standard. The external device I / F unit 224 is connected to an external device 250 such as a printer or a scanner by wire or wirelessly, and transmits / receives data to / from the external device 250 in accordance with a predetermined communication standard. The I / O device I / F unit 226 is connected to the I / O device 260 such as various sensors and actuators, and is connected to the I / O device 260, for example, a detection signal by a sensor, a control signal to the actuator, and the like. Sends and receives various signals and data. The media input / output unit 228 is composed of a drive device such as a DVD drive or a CD drive, and reads / writes data to / from the media 270 such as a DVD or a CD.

In the computer 200 having the above configuration, the processor 212 calls and executes the program 230 in the work memory area of the memory 214, and controls each part of the computer 200 via the bus 210. The program 230 may be stored in the storage device 220 instead of the memory 214. The program 230 may be recorded on a non-temporary recording medium such as a CD or DVD in an installable file format or an executable file format, and may be provided to the computer 200 via the media input / output unit 228. The program 230 may be provided to the computer 200 by downloading via the network 240 via the communication I / F unit 222. Further, the computer 200 may realize various functions realized by the processor 212 executing the program 230 by hardware such as FPGA and ASIC.

The computer 200 is composed of, for example, a stationary computer or a portable computer, and is an electronic device of any form. The computer 200 may be a client type computer, a server type computer, or a cloud type computer. The computer 200 may be applied to devices other than the database generation device 6 and the state determination device 7.

(Database generator 6)
FIG. 5 is a schematic block diagram showing an example of the database generation device 6 according to the embodiment of the present invention. FIG. 6 is a data structure diagram showing an example of the database 2 according to the embodiment of the present invention.

The database generation device 6 operates as a test facility, and is used for each combination of the usage environment 10, the main valve 3, the drive device 4, and the solenoid valve 5 (combination of test targets) constituting the fluid pressure drive valve 1 to be tested. , Judgment reference data is collected by measuring the operating state when a predetermined opening / closing operation is performed by the fluid pressure drive valve 1 to be tested. As shown in FIG. 5, the database generation device 6 includes a storage unit 60, a virtual load unit 61, a test data acquisition unit 62, and a database registration unit 63.

The database generation device 6 is configured to be able to communicate with various devices and systems by wired communication or wireless communication, and is connected to, for example, an external device 14 or a worker terminal device 8.

The database generator 6 is composed of, for example, the computer 200 shown in FIG. In this case, the storage unit 60 is composed of the storage device 220, and the test data acquisition unit 62 and the database registration unit 63 are composed of the processor 212 and the like.

The storage unit 60 stores various data such as the database 2. As shown in FIG. 6, the database 2 is a fluid for each combination of a plurality of types of usage environments 10, a plurality of types of main valves 3, a plurality of types of drive devices 4, and one or a plurality of types of solenoid valves 5. It is configured so that it is possible to register the determination reference data which is the reference of the operation state when the predetermined opening / closing operation is performed by the pressure drive valve 1 in association with each other. The database 2 can not only register new records, but also search, extract, refer to, update, or delete registered records.

In the database 2 shown in FIG. 6, for the sake of simplicity of explanation, the reference numerals are described as the data of the fields of the usage environment 10, the main valve 3, the drive device 4, and the electromagnetic valve 5, but the fields of the usage environment 10 are used. Is input information that specifies the conditions of the usage environment 10, and information that specifies each type (for example, model name, model name, model number, etc.) is input to the fields of the main valve 3, the drive device 4, and the electromagnetic valve 5. Are entered respectively.

The virtual load unit 61 can virtually reproduce the load state when the main valve 3 is driven in the usage environment 10 for each combination of the plurality of types of main valves 3 and the plurality of types of usage environments 10. It consists of devices. The virtual load unit 61 is composed of, for example, a disc brake device and is connected to the second shaft 12b. The disc brake device adjusts the braking force with respect to the second shaft 12b, so that the load acting on the second shaft 12b when the main valve 3 to be tested is driven in the usage environment 10 to be tested. Reproduce the state.

The test data acquisition unit 62 acquires the determination reference data when the opening / closing operation is performed by the virtual fluid pressure drive valve 1A corresponding to the combination of the test targets. The opening / closing operation may be performed a plurality of times, and in that case, the test data acquisition unit 62 may acquire the determination standard data by averaging the data of each time or selecting the representative data. Just do it.

The virtual fluid pressure drive valve 1A corresponding to the combination of the test targets includes the virtual load unit 61 in which the load state for reproducing the usage environment 10 and the main valve 3 to be tested is set, and the drive device 4 to be tested. And the solenoid valve 5. That is, the virtual fluid pressure drive valve 1A has a virtual load unit 61, a drive device 4 to be tested connected to the virtual load unit 61 via a first shaft 12a and a second shaft 12b, and a first. A third shaft 12c connected to the shaft 12a of the above is inserted into the solenoid valve 5 to be tested.

When acquiring the judgment standard data for the plurality of types of usage environments 10 and the judgment standard data for the plurality of types of main valves 3, the load state on the virtual load unit 61 is obtained without replacing the drive device 4 and the solenoid valve 5. By changing the setting, a virtual fluid pressure drive valve 1A corresponding to the combination of those test targets is configured. When acquiring the determination standard data for a plurality of types of drive devices 4, the drive device 4 to be tested needs to be replaced, and when acquiring the determination standard data for a plurality of types of solenoid valves 5, the test target Solenoid valve 5 needs to be replaced.

The test data acquisition unit 62 is connected to the solenoid valve 5 to be tested via a communication cable 140 (not required in the case of wireless communication), and is based on the measurement results measured by the sensor group 53 of the solenoid valve 5. Acquire the judgment standard data.

In this case, the test data acquisition unit 62 sets the operating state when the opening / closing operation is performed by the virtual fluid pressure drive valve 1A, such as time-series data of the valve opening of the main valve 3 in the opening / closing operation and opening / closing. The determination reference data including at least the time series data of the solenoid valve output side pressure of the air A supplied / discharged from the solenoid valve 5 to the drive device 4 during the operation is acquired.

The valve opening degree of the main valve 3 is measured by the main valve opening degree sensor 532. The pressure on the output side of the electromagnetic valve of the air A is the pressure of the air A supplied / discharged from the electromagnetic valve 5 to the drive device 4, and the air A (supply) when the air A is supplied from the electromagnetic valve 5 to the drive device 4. It includes the pressure of air) and the pressure of air A (exhaust) when the air A is discharged from the drive device 4 through the electromagnetic valve 5. The solenoid valve output side pressure of air A is measured by the second pressure sensor 531.

When the database generation device 6 includes the sensor group 64 for the test equipment, the test data acquisition unit 62 acquires the determination reference data based on the measurement results measured by the sensor group 64 for the test equipment. You may. The sensor group 64 for the test equipment is, for example, the first axis 12a.
The first torque sensor 640A that measures the first acting torque acting between the first shaft 12b and the second shaft 12b, and the first acting torque acting between the first shaft 12a and the second shaft 12b. Includes at least one of the second torque sensors 640B for measuring.

In this case, the test data acquisition unit 62 sets the time-series data of the valve opening of the main valve 3 and the electromagnetic valve output of the air A as the operating state when the opening / closing operation is performed by the virtual fluid pressure drive valve 1A. In addition to or in place of the time-series data of the side pressure, the determination reference data including at least the time-series data of the acting torque acting on the valve shaft 12 during the opening / closing operation is acquired. The acting torque is measured by at least one of the first torque sensor 640A and the second torque sensor 640B.

The time-series data is composed of a plurality of data measured at a plurality of different time points within a predetermined period, and is acquired at a predetermined sampling cycle, for example. In the present embodiment, the time-series data of the valve opening of the main valve 3, the time-series data of the electromagnetic valve output side pressure of the air A, and the time-series data of the acting torque have the same sampling period and the same phase (position). It is assumed that the data was measured at a plurality of time points with no phase difference), but at least one of the sampling period and the phase may be different.

The predetermined period is a period during which the opening / closing operation of the main valve 3 is performed, and corresponds to, for example, an execution period when the stroke test in the fluid pressure drive valve 1 is executed. The predetermined period may be the entire period from the start of the test to the end of the test in the execution period of the stroke test, or may be a part of the period. Therefore, the predetermined period may be, for example, the entire period of the full stroke test (fully open state → fully closed state → fully open state) or the entire period of the partial stroke test (fully open state → partially closed state), or the full stroke test. Partial period (fully open state → fully closed state, or fully closed state → fully open state, etc.) or part of the partial stroke test (fully open state → partially closed state, partially closed state → fully open state, etc.) ), And is not limited to these.

As an option, the determination reference data may be acquired based on the measurement results measured by the sensor group 53 other than the main valve opening sensor 532 and the second pressure sensor 531. For example, the determination reference data includes time-series data of the solenoid valve input side pressure of air A supplied from the air supply source 13 to the solenoid valve 5, and the differential pressure between the solenoid valve input side pressure and the solenoid valve output side pressure of air A. Time-series data, time-series data of control parameters (supply voltage, current value when energized, resistance value when non-energized, magnetic strength, etc.) of solenoid valve 52, time-series data of temperature of solenoid valve 5, fluid Total operating time of pressure driven valve 1, operating time since the last power was turned on to fluid pressure driven valve 1, number of operations of main valve 3, number of operations of drive device 4, solenoid valve 5 (mainly solenoid valve) The number of operations of the unit 52) and the opening / closing time of the main valve 3 may be further included.

The test data acquisition unit 62 inputs the operating state when the opening / closing operation is performed by the fluid pressure drive valve 1 in the normal state to the learning model, so that the operating state when the opening / closing operation is performed can be obtained. A learning model obtained by machine learning the correlation with the normal state of the fluid pressure drive valve 1 may be acquired as determination reference data. The machine learning here is called unsupervised learning, and for example, any machine learning method such as a neural network (including deep learning), clustering, multivariate analysis, and a support vector machine may be adopted.

The database registration unit 63 corresponds to the judgment standard data acquired by the virtual fluid pressure drive valve 1A for the combination of the usage environment 10, the main valve 3, the drive device 4, and the solenoid valve 5 to be tested. Attach and register in database 2. That is, the database registration unit 63 is a new link between the combination of test objects constituting the virtual fluid pressure drive valve 1A when the test data acquisition unit 62 acquires the determination reference data and the determination reference data. A record (data for one row in FIG. 6) is registered (added) in the database 2.

(Database generation method)
FIG. 7 is a flowchart showing an example of a database generation method by the database generation device 6 according to the embodiment of the present invention.

First, in step S100, the operator operates the terminal device 8 for the operator, and the combination of the usage environment 10, the main valve 3, the drive device 4, and the solenoid valve 5 constituting the fluid pressure drive valve 1 to be tested. When (combination of test targets) is specified, the database registration unit 63 of the database generation device 6 accepts the specified operation.

Next, in step S110, the operator attaches the drive device 4 and the solenoid valve 5 to be tested to the virtual load unit 61. At this time, the virtual load unit 61 and the drive device 4 to be tested are connected to each other via the first shaft 12a and the second shaft 12b, and the drive device 4 to be tested and the solenoid valve 5 to be tested are connected. Are connected via a first shaft 12a and a third shaft 12c. Further, if necessary, the first torque sensor 640A is attached between the first shaft 12a and the second shaft 12b, and the second torque sensor 640B is attached to the first shaft 12a and the third shaft 12a. It is mounted between the shafts 12c.

Next, in step S120, the operator sets a load state for the virtual load unit 61 to reproduce the combination of the usage environment 10 and the main valve 3 to be tested, so that the virtual load unit 61 corresponds to the combination of the test targets. Fluid pressure drive valve 1A is configured. When the virtual load unit 61 is configured so that the load state can be automatically set, the virtual load unit 61 automatically sets the load state according to the data corresponding to the combination of the test targets specified in step S100. Set.

Next, in step S130, when the worker operates the worker terminal device 8 and inputs that the setting work is completed, the test data acquisition unit 62 accepts the setting completion operation and virtual fluid. The pressure drive valve 1A is used to open and close the valve.

Then, in step S140, the test data acquisition unit 62 obtains determination reference data based on the measurement results measured by the sensor group 53 of the solenoid valve 5 when the opening / closing operation is performed in parallel with step S130. get. The test data acquisition unit 62, for example, based on the measurement results measured by the main valve opening sensor 532 and the second pressure sensor 531 as determination reference data, time-series data of the valve opening of the main valve 3 and Acquire time-series data of the electromagnetic valve output side pressure of air A.

Next, in step S150, the database registration unit 63 associates the determination criterion data acquired in step S140 with the combination of test objects specified in step S100 and registers it in the database 2.

Next, in step S160, when the worker operates the worker terminal device 8 and instructs whether or not there is another combination of test targets, the database registration unit 63 accepts the instruction operation.

If the instruction operation received in step S160 indicates that there is another combination of test objects (“Yes” in step S160), the process returns to step S100. Then, in step S100, the database registration unit 63 accepts the designated operation of the combination of other test targets, but only at least one of the usage environment 10 to be tested or the main valve 3 to be tested is changed. If this is the case, step S110 is omitted, and in step S120, a load state that reproduces the changed combination of the usage environment 10 and the main valve 3 is set. Further, when at least one of the drive device 4 to be tested or the solenoid valve 5 to be tested is changed, in step S110, the operator replaces the drive device 4 with the changed drive device 4 or replaces it with the changed drive device 4. Replace with the changed solenoid valve 5, or replace with the changed drive device 4 and solenoid valve 5.

On the other hand, when the instruction operation received in step S160 indicates that there is no other combination of test objects (“No” in step S160), the database generation method shown in FIG. 7 is terminated. In the database generation method, steps S130 and S140 correspond to a test data acquisition step, and step S150 corresponds to a database registration step.

As described above, according to the database generation device 6 and the database generation method according to the present embodiment, the load state according to the combination of the usage environment 10 and the main valve 3 to be tested is reproduced by the virtual load unit 61. Since the virtual fluid pressure drive valve 1A is configured in, there is no need to prepare actual equipment including each combination of the usage environment 10 and the main valve 3, and the opening / closing operation is performed by the virtual fluid pressure drive valve 1A. The judgment standard data when is performed is acquired. Therefore, the determination reference data can be easily collected for each combination of the test objects including the usage environment 10, the main valve 3, the drive device 4, and the solenoid valve 5.

(Status determination device 7)
FIG. 8 is a schematic block diagram showing an example of the state determination device 7 according to the embodiment of the present invention.

The state determination device 7 determines the state of the fluid pressure drive valve 1 used in the predetermined usage environment 10 by using the database 2. As shown in FIG. 8, the state determination device 7 includes a storage unit 70, a determination reference data acquisition unit 71, a determination target data acquisition unit 72, a state determination unit 73, and an output processing unit 74.

The state determination device 7 is composed of, for example, the computer 200 shown in FIG. In this case, the storage unit 70 is composed of the storage device 220, and the determination reference data acquisition unit 71, the determination target data acquisition unit 72, the state determination unit 73, and the output processing unit 74 are composed of the processor 212 and the like.

The storage unit 70 stores various data such as the database 2. The database 2 is provided by the database generator 6 via an arbitrary communication network or storage medium. In that case, the database 2 may include all data or may be limited to some data.

The determination standard data acquisition unit 71 refers to the database 2 stored in the storage unit 70, and includes the usage environment 10 constituting the fluid pressure drive valve 1B to be determined, the main valve 3, the drive device 4, and the solenoid valve 5. Acquire the judgment standard data associated with the combination (the combination to be judged).

For example, when the state determination device 7 specifies a combination of determination targets (use environment 10 ₂ , main valve ₃₂ , drive device ₄₂ , solenoid valve ₅₂ ) as shown by the solid line frame in FIG. , In the database 2 shown in FIG. 6, the determination reference data “Data4A” and “Data4B” associated with the ID “4” are acquired. When the state determination device 7 is incorporated in the controller 540 of the solenoid valve 5, the determination reference data acquisition unit 71 includes the usage environment 10 to which the solenoid valve 5 is attached, the main valve 3, and the drive device. By specifying 4 and, the combination to be determined may be specified, and the determination standard data associated with the combination may be acquired. Further, the specification data of the fluid pressure drive valve 1 indicating the combination to be determined may be stored in the storage unit 70 at the time of assembling the fluid pressure drive valve 1. In that case, the determination reference data acquisition unit 71 stores the specification data. The combination to be determined may be specified by reference.

The database 2 may be stored in the external device 14 or the like, and in that case, the determination standard data acquisition unit 71 may refer to the database 2 stored in the external device 14 or the like and acquire the determination standard data. At that time, the determination standard data acquisition unit 71 may store the determination standard data in the storage unit 70, and may refer to the storage unit 70 thereafter.

The determination target data acquisition unit 72 acquires the operation state when the opening / closing operation is performed by the fluid pressure drive valve 1B to be determined as the determination target data. The determination target data acquisition unit 72 is connected to the solenoid valve 5 constituting the fluid pressure drive valve 1B to be determined via a communication cable 140 (not required in the case of wireless communication), and the sensor group 53 of the solenoid valve 5 is connected. The judgment target data is acquired based on the measurement result measured by. As shown in FIG. 3, when the state determination device 7 is incorporated in the controller 540, the determination target data acquisition unit 72 obtains determination target data from the sensor group 53 without going through the communication cable 140. You just have to get it.

In this case, the determination target data acquisition unit 72 sets the operation state when the opening / closing operation is performed by the fluid pressure drive valve 1B to be determined, the time-series data of the valve opening of the main valve 3 in the opening / closing operation, and the time series data. The determination target data including at least the time-series data of the electromagnetic valve output side pressure of the air A supplied / discharged from the electromagnetic valve 5 to the drive device 4 during the opening / closing operation is acquired.

The determination target data acquisition unit 72 is connected to the sensor group 53 of the electromagnetic valve 5, but may be connected to a part of the sensor group 53 according to the type and format of the data included in the determination reference data. Then, data to be connected to all of the sensor group 53 and acquired as determination target data from the measurement results of the sensor group 53 may be selected.

The state determination unit 73 determines the state of the fluid pressure drive valve 1B to be determined based on the determination reference data and the determination target data. The state determination unit 73 determines (diagnoses), for example, whether the fluid pressure drive valve 1B is in a normal state or an abnormal state, that is, whether or not there is an abnormality.

The abnormal state may include, for example, a plurality of abnormal states according to the specific content and degree of the abnormality. In this case, the state determination unit 73 determines whether the fluid pressure drive valve 1B is in a normal state or in a plurality of abnormal states.

In addition, the abnormal state is not only an ex post facto abnormality such that the occurrence of the abnormality was found at the time of judgment, but also an allowable range to be judged as normal at the time of judgment, but it seems that the occurrence of an abnormality in the future was predicted. It may also include signs of abnormalities. In this case, the state determination unit 73 is in a normal state as the state of the fluid pressure drive valve 1B, or has a preset remaining life (for example, several hours, several days, several months, several years, etc.). ) To determine if the condition is abnormal. Further, the state determination unit 73 determines whether the state of the fluid pressure drive valve 1B is a normal state or an abnormal state within a plurality of preset remaining life periods. You may.

The method for determining the state of the fluid pressure drive valve 1B to be determined by the state determination unit 73 is appropriately selected according to the determination reference data and the type and format of the data included in the determination target data.

When the determination standard data and the determination target data include the time-series data of the valve opening degree of the main valve 3 and the time-series data of the electromagnetic valve output side pressure of the air A as the operating state, the state determination unit 73 determines. The presence or absence of an abnormality in the fluid pressure drive valve 1B is determined based on the degree of similarity when the data and the determination target data are compared.

Further, when the determination reference data includes the time-series data of the acting torque, the state determination unit 73 includes the time-series data of the valve opening degree of the main valve 3 and the electromagnetic valve output side pressure of the air A included in the determination target data. The time-series data of the acting torque is estimated by inputting the time-series data of The presence or absence of abnormality in the fluid pressure drive valve 1B is determined based on the degree of similarity when compared.

For the similarity, for example, the difference value between the time-series data included in the judgment standard data and the time-series data included in the judgment target data at each time when each is represented by a graph of time transition is obtained, and each is obtained. It is calculated based on the total value obtained by totaling the time difference values and the statistical value (for example, average value, standard deviation, etc.) for each time difference value. In this case, the smaller the total value or the statistical value is, the higher the similarity is treated. If the similarity is equal to or higher than a predetermined threshold value, the state determination unit 73 determines that the state is normal, and if not, the condition is normal. Judged as an abnormal condition. The similarity may be calculated based on, for example, a difference value of statistical values representing each graph (for example, a regression coefficient of a regression equation).

In addition, the judgment reference data is a learning model in which the correlation between the operating state when the opening / closing operation is performed by the fluid pressure drive valve 1 in the normal state and the normal state of the fluid pressure drive valve 1 is machine-learned. At one time, the state determination unit 73 determines whether or not there is an abnormality in the fluid pressure drive valve 1B by inputting the determination target data into the learning model. The training model outputs output data by inputting determination target data as input data, for example, and the state determination unit 73 has a feature amount based on the input data and a feature amount based on the output data. If the difference value is equal to or less than a predetermined threshold value, it is determined to be a normal state, and if not, it is determined to be an abnormal state. The feature quantity is, for example, a parameter expressed as a feature vector in a multidimensional space, and the difference is expressed as a distance between the feature vectors.

The output processing unit 74 performs output processing for outputting diagnostic information of the fluid pressure drive valve 1B to be determined as the determination result of the state determination unit 73. As a specific output means, various means can be adopted. The output processing unit 74, for example, notifies the operator of the diagnostic information by display or sound, stores it as the diagnostic history of the fluid pressure drive valve 1B, for example, in the storage unit 70, or transmits it to the external device 14. You may.

(Status judgment method)
FIG. 9 is a flowchart showing an example of a state determination method by the state determination device 7 according to the embodiment of the present invention. Hereinafter, the controller 540 in which the state determination device 7 is incorporated will be described as determining whether the fluid pressure drive valve 1B to be determined is in a normal state or an abnormal state.

FIG. 9 shows a case where a predetermined test operation condition is satisfied while power is supplied from the external power source 15 to the fluid pressure drive valve 1 and air A is supplied from the air supply source 13 to the fluid pressure drive valve 1. The series of state determination methods shown in the above is executed by the controller 540 (state determination device 7).

First, in step S200, the controller 540 (judgment reference data acquisition unit 71) refers to the database 2, and the usage environment 10, the main valve 3, the drive device 4, and the solenoid valve constituting the fluid pressure drive valve 1B to be determined are to be determined. The determination standard data associated with the combination with 5 (the combination to be determined) is acquired.

Next, in step S210, the valve test switch 541 receives a command from the controller 540 and executes a stroke test of the fluid pressure drive valve 1B as a test operation for performing a predetermined opening / closing operation.

Next, in step S220, the controller 540 (determination target data acquisition unit 72) determines the operation state when the opening / closing operation is performed based on the measurement result measured by the sensor group 53 of the solenoid valve 5. Get as.

Next, in step S230, the controller 540 (state determination unit 73) determines the state of the fluid pressure drive valve 1B based on the determination reference data acquired in step S200 and the determination target data acquired in step S220.

Next, in step S240, the controller 540 (output processing unit 74) indicates whether the diagnostic information of the fluid pressure drive valve 1B, which is the determination result of the state determination unit 73 in step S230, is "normal" or "abnormal". If it is determined to be "normal" (step S240: "normal"), the process proceeds to step S250, and if it is determined to be "abnormal" (step S240: "abnormal"), the process proceeds to step S260. ..

Then, in step S250, the controller 540 (output processing unit 74) outputs information indicating "normal". Note that step S250 may be omitted.

Further, in step S260, the controller 540 (output processing unit 74) outputs information indicating "abnormality" and ends a series of state determination methods shown in FIG. In the state determination method, step S200 corresponds to a determination reference data acquisition step, step S220 corresponds to a determination target data acquisition step, step S230 corresponds to a state determination step, and steps S240 to S260 correspond to an output processing step.

As described above, according to the state determination device 7 and the state determination method according to the present embodiment, the state of the fluid pressure drive valve 1 can be determined (diagnosed) with high accuracy without depending on the experience of the operator. can.

(Other embodiments)
The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the gist of the present invention. And all of them are included in the technical idea of the present invention.

In the above embodiment, the case where the main valve 3 constituting the fluid pressure drive valve 1 is of a plurality of types has been described, but the main valve 3 may be of one type. Although the case where the drive device 4 constituting the fluid pressure drive valve 1 is of a plurality of types has been described, the drive device 4 may be of one type. In the above embodiment, the case where the solenoid valves 5 constituting the fluid pressure drive valve 1 are of a plurality of types has been described, but the solenoid valves 5 may be of one type.

(Variation example of database 2)
FIG. 10 is a data structure diagram showing a modified example of the database 2 according to the embodiment of the present invention. In the database 2 shown in FIG. 10, instead of the fields of the usage environment 10 and the main valve 3 shown in FIG. 6, the load state L (L1, L2, ..., Lt) (subscript t is an arbitrary integer, and the load is loaded. Has a field) (indicating the number of types L). In the field of the load state L, as data according to the combination of the usage environment 10 and the main valve 3, for example, when the second shaft 12b (valve shaft 12) is rotated in the range of 0 to 90 degrees. The magnitude of the load and the amount of change are registered.

When the database registration unit 63 of the database generation device 6 associates the determination data with the combination to be tested and registers it in the database 2 shown in FIG. 10 (step S150 in FIG. 7), the virtual load unit in step S120. The load state L set for 61 is registered in the database 2 (field of load state L).

When the state determination unit 73 of the state determination device 7 determines the state of the fluid pressure drive valve 1B to be determined using the database 2 shown in FIG. 10 (step S230 in FIG. 9), step S2.
As a preparation for 00, the load state L when the operator manually rotates the second shaft 12b in the fluid pressure drive valve 1B to be determined is set by using, for example, a temporarily installed torque sensor or the like. measure. Then, when the measurement result of the load state L is input to the state determination device 7 as data corresponding to the combination of the usage environment 10 and the main valve 3, in step S200, the determination reference data acquisition unit 71 shows in FIG. With reference to database 2, the load state L (internal use environment 10 and main valve 3) constituting the fluid pressure drive valve 1B to be determined, and the combination of the drive device 4 and the solenoid valve 5 (combination of determination targets). Acquire the judgment standard data associated with.

For example, when the measurement result of the load state L by the operator matches the load state L2 (may match if it is within a predetermined range), the state determination device 7 is shown by the solid line frame in FIG. As described above, the combination to be determined (load state L2 (corresponding to the combination of the usage environment 10 ₂ and the main valve 32), the drive device ₄₂ , and the solenoid valve 5 ₂ ) is specified, and the ID is used in the database ₂ shown in FIG. The determination standard data "Data4A" and "Data4B" associated with "4" are acquired. Since the steps after step S210 are the same as those in the above embodiment, the description thereof will be omitted.

(Modification example of learning model)
In the above embodiment, the case where the determination criterion data is a learning model by unsupervised learning has been described, but the learning model may be composed of a plurality of learning models as a variation example thereof. In the following, a case where the judgment criterion data is composed of a plurality of learning models by unsupervised learning will be described focusing on the parts different from the above-described embodiment.

FIG. 11 is a diagram illustrating a learning phase of machine learning in a modified example of the learning model according to the embodiment of the present invention. FIG. 12 is a diagram illustrating an inference phase of machine learning in a modified example of the learning model according to the embodiment of the present invention.

First, the learning phase of machine learning in a modified example of the learning model will be described. The test data acquisition unit 62 divides the operation state when the opening / closing operation is performed by the fluid pressure drive valve 1 in the normal state into a plurality of operation categories according to a predetermined standard, and operates the operation state for each operation category. By inputting to each of the multiple learning models corresponding to the divisions, the correlation between the operating state when the opening / closing operation is performed and the normal state of the fluid pressure drive valve 1 is machine-learned for each of the plurality of operation divisions. Acquire a plurality of learning models (normal models) as judgment standard data.

When dividing the operating state into a plurality of operating categories, for example, the valve opening degree of the main valve 3 in the opening / closing operation may be used as a reference among the operating states. In this case, as shown in FIG. 11, first, the test data acquisition unit 62 obtains time-series data of the valve opening degree of the main valve 3 when the opening / closing operation is performed by the fluid pressure drive valve 1 in the normal state. A plurality of sets of operating states such as time-series data of the solenoid valve output side pressure of the air A are collected, and the collected operating states are divided based on a predetermined range of the valve opening degree. In FIG. 11, as an example, the collected operation states such as the operation category of the valve opening 0-10%, the operation category of the valve opening 10-20%, the operation category of the valve opening 20-30%, and the like. Is divided into 10 operation categories in 10% increments of 0-100% with respect to the valve opening degree.

Next, the test data acquisition unit 62 inputs the collected operation states corresponding to the operation categories into the learning model prepared for each of the divided operation categories. For example, the operation state divided into the operation categories of the valve opening degree 0-10% is input to the learning model corresponding to the operation category of the valve opening degree 0-10%.

Then, each learning model corresponding to the operation category determines the correlation between the operation state when the opening / closing operation is performed and the normal state of the fluid pressure drive valve 1 based on the operation state for each input operation category. By machine learning, it becomes a normal model showing the normal state of the fluid pressure drive valve 1 for each operation category. The test data acquisition unit 62 is a plurality of learning models (normal models) for each of these operation categories.
Is acquired as judgment standard data.

The data acquisition unit 62 may acquire the normal model thus created as the determination reference data. Machine learning here is called unsupervised learning, and FIG. 11 gives an example of creating a normal model using clustering, which is one of the methods of unsupervised learning.

Next, the inference phase of machine learning in the modified example of the learning model will be described. The operating state when the opening / closing operation is performed by the fluid pressure drive valve 1 in the normal state of the judgment reference data is divided into a plurality of operation categories according to a predetermined standard, and the operating state when the opening / closing operation is performed. When there are a plurality of learning models (normal models) in which the correlation between the fluid pressure drive valve 1 and the normal state of the fluid pressure drive valve 1 is machine-learned for each of a plurality of operation categories, the state determination unit 73 uses the determination target data as described above. By inputting to the normal model of the operation category including the determination target data among the plurality of normal models generated in the learning phase, it is determined whether or not there is an abnormality in the fluid pressure drive valve 1B to be determined.

First, the determination target data acquisition unit 72 acquires determination target data from the fluid pressure drive valve 1B to be determined. The state determination unit 73 selects a normal model of the operation category including the determination target data from the plurality of normal models generated in the learning phase. In FIG. 12, as an example of the normal model generated in the learning phase, the operation classification of the valve opening 0-10%, the operation classification of the valve opening 10-20%, the operation classification of the valve opening 20-30%, and so on. As shown in the above, a normal model with a valve opening of 50-60% is obtained by dividing the collected operating states into 10 operating categories out of 0-100% based on the valve opening. Of the plurality of normal models machine-learned by the state determination unit 73 for each operation category by acquiring the determination target data of the valve opening 55% by the determination target data acquisition unit 72, the valve opening 50- It shows that 60% of normal models are selected.

Then, the state determination unit 73 inputs the determination target data (determination target data of the valve opening degree 55%) into the selected normal model, and determines whether or not there is an abnormality in the fluid pressure drive valve 1B. As a method of using a normal model and inputting determination target data to determine the presence or absence of an abnormality in the fluid pressure drive valve 1B, for example, clustering, which is one of unsupervised learning algorithms, can be used.

In the abnormality determination method using clustering, in the learning phase, a learning model is machine-learned using a plurality of input data of a specific state (for example, a normal state) which is training data, and based on the learned learning model, A set of feature quantities corresponding to the input data in a specific state is generated, a threshold for normal / abnormal judgment is set based on the generated set, and the input data to be judged is acquired in the inference phase. , The input data to be judged is input to the learning model to generate the corresponding feature amount, and the input data to be judged depends on whether the generated feature amount exceeds the threshold for normal / abnormal judgment. Determines whether is normal or abnormal. Other clustering methods include those using Mahalanobis distance and those using dynamic time warping, and any method can be used in the present invention.

In addition to the above, the standard for dividing the operating state when the opening / closing operation is performed by the fluid pressure drive valve 1 in the normal state into a plurality of operation categories is not limited to the valve opening, and the solenoid valve during the opening / closing operation. Other variables such as the solenoid valve output side pressure of the driving fluid supplied and discharged from the driving device 4 and the acting torque acting on the valve shaft 12 during the opening / closing operation may be used. Further, a combination of two or more different types of variables may be used as a reference for dividing the operation state into a plurality of operation categories. Further, the number of operation divisions to be divided is not limited to 10, and any number may be set.

(program)
The present invention can provide the computer 200 shown in FIG. 4 in the form of a program (database generation program) 230 that functions as each part of the database generation device 6 according to the above embodiment. Further, the present invention can provide the computer 200 shown in FIG. 4 in the form of a program (state determination program) 230 that functions as each part of the state determination device 7 according to the above embodiment.

1 ... Fluid pressure drive valve, 1A ... Virtual fluid pressure drive valve, 1B ... Fluid pressure drive valve to be determined,
2 ... database, 3 ... main valve, 4 ... drive device, 5 ... solenoid valve,
6 ... database generator, 7 ... status determination device, 8 ... worker terminal device,
10 ... Usage environment, 11 ... Piping,
12 ... valve shaft, 12a ... first shaft, 12b ... second shaft, 12c ... third shaft,
13 ... air supply source, 14 ... external device, 15 ... external power supply,
30 ... valve box, 31 ... valve body,
40 ... Cylinder, 41 ... Piston rod, 42A ... First piston,
42B ... 2nd piston, 43 ... Coil spring, 44 ... Air supply / exhaust port,
45 ... Transmission mechanism, 47 ... Spring chamber, 48 ... Cylinder chamber,
50 ... accommodating part, 51 ... spool part, 52 ... solenoid part, 53 ... sensor group,
54 ... control unit, 55 ... communication unit, 56 ... power supply circuit unit,
60 ... storage unit, 61 ... virtual load unit, 62 ... test data acquisition unit,
63 ... Database registration unit, 64 ... Sensor group,
70 ... Storage unit, 71 ... Judgment standard data acquisition unit, 72 ... Judgment target data acquisition unit,
73 ... Status determination unit, 74 ... Output processing unit,
100 ... Driving support system, 120 ... Permanent magnet,
130 ... 1st air pipe, 131 ... 2nd air pipe,
140 ... communication cable, 150 ... power cable, 200 ... computer,
500 ... shaft insertion slot, 501 ... cable insertion slot, 502 ... first flow path,
503 ... Second flow path, 510 ... Input port, 511 ... Output port, 512 ... Exhaust port, 530 ... First pressure sensor, 513 ... Second pressure sensor, 532 ... Main valve opening sensor,
533 ... Voltage sensor, 534 ... Resistance sensor, 535 ... Temperature sensor,
536 ... Magnetic sensor, 537 ... Operating time meter, 538 ... Operation counter,
540 ... controller, 541 ... valve test switch,
640A ... 1st torque sensor, 640B ... 2nd torque sensor

Claims (13)

It is composed of a main valve used in a predetermined usage environment, a drive device for driving a valve shaft connected to the main valve, and a solenoid valve for controlling supply and discharge of a drive fluid to the drive device. A database generator that generates a database used to determine the state of a fluid pressure driven valve.
A predetermined opening / closing operation can be performed by the fluid pressure drive valve for each combination of the plurality of types of usage environments, the plurality of types of the main valve, the plurality of types of drive devices, and one or more types of the solenoid valves. A storage unit that stores the database that can be registered in association with each other as a criterion data that serves as a reference for the operating state when the operation is performed.
A virtual load unit that can virtually reproduce the load state when the main valve is driven in the usage environment for each combination of the plurality of types of the usage environment and the plurality of types of the main valve.
The virtual fluid pressure composed of the virtual load unit in which the usage environment to be tested and the load state that reproduces the main valve are set, the drive device to be tested, and the solenoid valve. A test data acquisition unit that acquires the judgment reference data when the opening / closing operation is performed by the drive valve, and a test data acquisition unit.
The determination reference data acquired by the virtual fluid pressure drive valve is associated with the combination of the usage environment, the main valve, the drive device, and the solenoid valve to be tested. It has a database registration unit to register in the database.
Database generator. The test data acquisition unit
The time-series data of the valve opening degree of the main valve in the opening / closing operation and the time-series data of the solenoid valve output side pressure of the driving fluid supplied / discharged from the solenoid valve to the driving device during the opening / closing operation are described. Acquire the above-mentioned judgment standard data including at least as an operating state,
The database generator according to claim 1. The test data acquisition unit
The determination reference data including at least the time-series data of the acting torque acting on the valve shaft during the opening / closing operation as the operating state is acquired.
The database generator according to claim 1 or 2. The test data acquisition unit
By inputting the operating state when the opening / closing operation is performed into the learning model, the learning model in which the correlation between the operating state and the normal state of the fluid pressure drive valve is machine-learned is determined. Acquired as reference data,
The database generator according to any one of claims 1 to 3. The test data acquisition unit
The operation state when the opening / closing operation is performed is divided into a plurality of operation categories according to a predetermined standard.
By inputting the operation state for each operation category into the plurality of learning models corresponding to the plurality of operation categories, the plurality of learning models in which the correlation is machine-learned for each of the plurality of operation categories. Is acquired as the determination criterion data,
The database generator according to claim 4. The test data acquisition unit
The operation state when the opening / closing operation is performed is divided into a plurality of the operation categories based on the valve opening degree of the main valve in the opening / closing operation.
The database generator according to claim 5. Using the database generated by the database generator according to any one of claims 1 to 6, a main valve used in a predetermined usage environment and a valve shaft connected to the main valve can be used. A state determination device for determining the state of a fluid pressure drive valve composed of a drive device to be driven and an electromagnetic valve for controlling supply and discharge of drive fluid to the drive device.
Judgment criteria for acquiring the determination criteria data associated with the usage environment constituting the fluid pressure drive valve to be determined, the combination of the main valve, the drive device, and the solenoid valve with reference to the database. Data acquisition department and
A judgment target data acquisition unit that acquires an operating state when a predetermined opening / closing operation is performed by the fluid pressure drive valve to be determined as judgment target data, and a judgment target data acquisition unit.
A state determination unit for determining the state of the fluid pressure drive valve to be determined based on the determination reference data and the determination target data is provided.
Status judgment device. The determination standard data and the determination target data are
When the operating state includes time series data,
The state determination unit
It is determined whether or not there is an abnormality in the fluid pressure drive valve based on the degree of similarity when the determination reference data and the determination target data are compared.
The state determination device according to claim 7. The judgment criteria data is
When the learning model is machine-learned about the correlation between the operating state and the normal state of the fluid pressure drive valve.
The state determination unit
By inputting the determination target data into the learning model, it is determined whether or not the fluid pressure drive valve is abnormal.
The state determination device according to claim 7. The judgment criteria data is
When the correlation is a plurality of the learning models in which the operation state when the opening / closing operation is performed is machine-learned for each of a plurality of operation categories divided by a predetermined reference.
The state determination unit
By inputting the determination target data into the learning model corresponding to the operation category including the determination target data, it is determined whether or not the fluid pressure drive valve is abnormal.
The database generator according to claim 9. The judgment criteria data is
The correlation is machine-learned for each of the plurality of operation categories in which the operation state when the opening / closing operation is performed is divided based on the valve opening degree of the main valve in the opening / closing operation. When it is the learning model,
The state determination unit
By inputting the determination target data into the learning model corresponding to the operation category including the valve opening degree of the main valve in the opening / closing operation when the determination target data is acquired, the fluid pressure drive valve is used. Judging the presence or absence of abnormalities in
The database generator according to claim 10. It is composed of a main valve used in a predetermined usage environment, a drive device for driving a valve shaft connected to the main valve, and a solenoid valve for controlling supply and discharge of a drive fluid to the drive device. A database generation method that generates a database used to determine the state of a fluid pressure driven valve.
For each combination of the plurality of types of the usage environment and the plurality of types of the main valve, a virtual load unit that can virtually reproduce the load state when the main valve is driven in the usage environment is used. , The virtual load unit in which the load state that reproduces the usage environment and the main valve to be tested is set, and the virtual fluid composed of the drive device and the solenoid valve to be tested. A test data acquisition process for acquiring judgment standard data that serves as a reference for the operating state when a predetermined opening / closing operation is performed on the pressure-driven valve, and a test data acquisition process.
A database in which the determination reference data acquired by the virtual fluid pressure drive valve is associated with the combination of the usage environment, the main valve, the drive device, and the solenoid valve to be tested. A database registration process to be registered in
Database generation method. Using the database generated by the database generation method according to claim 12, a main valve used in a predetermined usage environment, a drive device for driving a valve shaft connected to the main valve, and the drive device. This is a state determination method for determining the state of a fluid pressure drive valve composed of a solenoid valve that controls the supply and discharge of the drive fluid.
Judgment criteria for acquiring the determination criteria data associated with the usage environment constituting the fluid pressure drive valve to be determined, the combination of the main valve, the drive device, and the solenoid valve with reference to the database. Data acquisition process and
The judgment target data acquisition step of acquiring the operation state when a predetermined opening / closing operation is performed by the fluid pressure drive valve to be the judgment target as the judgment target data, and the judgment target data acquisition step.
The present invention comprises a state determination step of determining the state of the fluid pressure drive valve to be determined based on the determination reference data and the determination target data.
Status judgment method.

Images